© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13278
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to transportation and logistics

    oai_token-act-pair · gemini-2.0-flash

    carry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TestingModule
    -0.80
    tvguidetime
    -0.65
    TestBed
    -0.65
    ItemBackground
    -0.65
    GeoNames
    -0.63
    fjspx
    -0.60
    czegóły
    -0.59
    RRect
    -0.58
     Oc
    -0.58
     <=",
    -0.56
    POSITIVE LOGITS
     carry
    0.82
     carrying
    0.76
     carries
    0.75
     Carry
    0.73
    carry
    0.71
     Carrying
    0.70
     CARRY
    0.70
     bringing
    0.70
     carried
    0.68
     fer
    0.66
    Activations Density 2.869%

    No Known Activations